Related papers: SHOT: Suppressing the Hessian along the Optimizati…
The meta learning few-shot classification is an emerging problem in machine learning that received enormous attention recently, where the goal is to learn a model that can quickly adapt to a new task with only a few labeled data. We…
Model generalizability to unseen datasets, concerned with in-the-wild robustness, is less studied for indoor single-image depth prediction. We leverage gradient-based meta-learning for higher generalizability on zero-shot cross-dataset…
We propose an adaptation of the curriculum training framework, applicable to state-of-the-art meta learning techniques for few-shot classification. Curriculum-based training popularly attempts to mimic human learning by progressively…
This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are…
Large Language Models (LLMs) have been shown to be able to learn different tasks without explicit finetuning when given many input-output examples / demonstrations through In-Context Learning (ICL). Increasing the number of examples, called…
Recently, a simple yet effective algorithm -- goal-conditioned supervised-learning (GCSL) -- was proposed to tackle goal-conditioned reinforcement-learning. GCSL is based on the principle of hindsight learning: by observing states visited…
Meta-learning is a powerful approach that exploits historical data to quickly solve new tasks from the same distribution. In the low-data regime, methods based on the closed-form posterior of Gaussian processes (GP) together with Bayesian…
Machine unlearning (MU) has emerged to enhance the privacy and trustworthiness of deep neural networks. Approximate MU is a practical method for large-scale models. Our investigation into approximate MU starts with identifying the steepest…
Meta-learning (ML) has emerged as a promising learning method under resource constraints such as few-shot learning. ML approaches typically propose a methodology to learn generalizable models. In this work-in-progress paper, we put the…
Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…
Mini-batch sub-sampling (MBSS) is favored in deep neural network training to reduce the computational cost. Still, it introduces an inherent sampling error, making the selection of appropriate learning rates challenging. The sampling errors…
Gradient-based meta-learning (GBML) algorithms are able to fast adapt to new tasks by transferring the learned meta-knowledge, while assuming that all tasks come from the same distribution (in-distribution, ID). However, in the real world,…
This paper introduces Low-shot Object Learning with Mutual Exclusivity Bias (LSME), the first computational framing of mutual exclusivity bias, a phenomenon commonly observed in infants during word learning. We provide a novel dataset,…
Meta-learning for few-shot learning allows a machine to leverage previously acquired knowledge as a prior, thus improving the performance on novel tasks with only small amounts of data. However, most mainstream models suffer from…
The aim of Few-Shot learning methods is to train models which can easily adapt to previously unseen tasks, based on small amounts of data. One of the most popular and elegant Few-Shot learning approaches is Model-Agnostic Meta-Learning…
Few-shot learning is challenging for learning algorithms that learn each task in isolation and from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurately and faster with…
Meta-learning has been the most common framework for few-shot learning in recent years. It learns the model from collections of few-shot classification tasks, which is believed to have a key advantage of making the training objective…
This paper proposes several novel optimization algorithms for minimizing a nonlinear objective function. The algorithms are enlightened by the optimal state trajectory of an optimal control problem closely related to the minimized objective…
Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we…
Solving a bilevel optimization problem is at the core of several machine learning problems such as hyperparameter tuning, data denoising, meta- and few-shot learning, and training-data poisoning. Different from simultaneous or…